ResearchTasksMulti-image Multi-modal UnderstandingMulti-image Multi-modal UnderstandingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedQ-BenchLLaVA-OneVision-7B74.4Accuracy2Feb 26, 2026MantisVisionTrim on LLaVA-OneVision-7B65.4Accuracy2Feb 26, 2026MuirBenchLLaVA-OneVision-7B41.8Accuracy2Feb 26, 2026